December 9th, 2016
Understanding the Logical and Semantic
Structure of Large Documents
11:00-1:00 Monday, 12 December 2016, ITE325b, UMBC
Up-to-the-minute language understanding approaches are mostly focused on small documents such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents such as legal documents, reports, business opportunities, proposals and technical manuals is still a challenging task. The reason behind this challenge is that the documents may be multi-themed, complex and cover diverse topics.
We aim to automatically identify and classify a document’s sections and subsections, infer their structure and annotate them with semantic labels to understand the semantic structure of a document. This document’s structure understanding will significantly benefit and inform a variety of applications such as information extraction and retrieval, document categorization and clustering, document summarization, fact and relation extraction, text analysis and question answering.
Committee: Drs. Tim Finin (Chair), Anupam Joshi, Tim Oates, Cynthia Matuszek, James Mayfield (JHU)
May 22nd, 2016
With the increase in the number of cloud services and service providers, manual analysis of Service Level Agreements (SLA), comparison between different service offerings and conformance regulation has become a difficult task for customers. Cloud SLAs are policy documents describing the legal agreement between cloud providers and customers. SLA specifies the commitment of availability, performance of services, penalties associated with violations and procedure for customers to receive compensations in case of service disruptions. The aim of our research is to develop technology solutions for automated cloud service management using Semantic Web and Text Mining techniques. In this paper we discuss in detail the challenges in automating cloud services management and present our preliminary work in extraction of knowledge from SLAs of different cloud services. We extracted two types of information from the SLA documents which can be useful for end users. First, the relationship between the service commitment and financial credit. We represented this information by enhancing the existing Cloud service ontology proposed by us in our previous research. Second, we extracted rules in the form of obligations and permissions from SLAs using modal and deontic logic formalizations. For our analysis, we considered six publicly available SLA documents from different cloud computing service providers.
May 2nd, 2016
He’s dead, Jim.
Google recently shut down the query interface to Freebase. All that is left of this innovative service is the ability to download a few final data dumps.
Freebase was launched nine years ago by Metaweb as an online source of structured data collected from Wikipedia and many other sources, including individual, user-submitted uploads and edits. Metaweb was acquired by Google in July 2010 and Freebase subsequently grew to have more than 2.4 billion facts about 44 million subjects. In December 2014, Google announced that it was closing Freebase and four months later it became read-only. Sometime this week the query interface was shut down.
I’ve enjoyed using Freebase in various projects in the past two years and found that it complemented DBpedia in many ways. Although its native semantics differed from that of RDF and OWL, it was close enough to allow all of Freebase to be exported as RDF. Its schema was larger than DBpedia’s and the data tended to be a bit cleaner.
Google generously decided to donate the data to the Wikidata project, which began migrating Freebase’s data to Wikidata in 2015. The Freebase data also lives on as part of Google’s Knowledge Graph. Google recently allowed very limited querying of its knowledge graph and my limited experimenting with it suggests that has Freebase data at its core.
May 1st, 2016
Representing and Reasoning with Temporal
Properties/Relations in OWL/RDF
10:30-11:30 Monday, 2 May 2016, ITE346
OWL ontologies offer the means for modeling real-world domains by representing their high-level concepts, properties and interrelationships. These concepts and their properties are connected by means of binary relations. However, this assumes that the model of the domain is either a set of static objects and relationships that do not change over time, or a snapshot of these objects at a particular point in time. In general, relationships between objects that change over time (dynamic properties) are not binary relations, since they involve a temporal interval in addition to the object and the subject. Representing and querying information evolving in time requires careful consideration of how to use OWL constructs to model dynamic relationships and how the semantics and reasoning capabilities within that architecture are affected.
April 3rd, 2016
Policies For Oblivious Cloud Storage
Using Semantic Web Technologies
10:30am, Monday, 4 April 2016, ITE 346, UMBC
Consumers want to ensure that their enterprise data is stored securely and obliviously on the cloud, such that the data objects or their access patterns are not revealed to anyone, including the cloud provider, in the public cloud environment. We have created a detailed ontology describing the oblivious cloud storage models and role based access controls that should be in place to manage this risk. We have also implemented the ObliviCloudManager application that allows users to manage their cloud data using oblivious data structures. This application uses role based access control model and collection based document management to store and retrieve data efficiently. Cloud consumers can use our system to define policies for storing data obliviously and manage storage on untrusted cloud platforms, even if they are not familiar with the underlying technology and concepts of the oblivious data structure.
February 17th, 2016
Botnet attacks turn susceptible victim computers into bots that perform various malicious activities while under the control of a botmaster. Some examples of the damage they cause include denial of service, click fraud, spamware, and phishing. These attacks can vary in the type of architecture and communication protocol used, which might be modified during the botnet lifespan. Intrusion detection and prevention systems are one way to safeguard the cyber-physical systems we use, but they have difficulty detecting new or modified attacks, including botnets. Only known attacks whose signatures have been identified and stored in some form can be discovered by most of these systems. Also, traditional IDPSs are point-based solutions incapable of utilizing information from multiple data sources and have difficulty discovering new or more complex attacks. To address these issues, we are developing a semantic approach to intrusion detection that uses a variety of sensors collaboratively. Leveraging information from these heterogeneous sources leads to a more robust, situational-aware IDPS that is better equipped to detect complicated attacks such as botnets.
December 16th, 2015
Zareen Syed, Ankur Padia, Tim Finin, Lisa Mathews and Anupam Joshi, UCO: Unified Cybersecurity Ontology
, AAAI Workshop on Artificial Intelligence for Cyber Security (AICS), February 2016.
In this paper we describe the Unified Cybersecurity Ontology (UCO) that is intended to support information integration and cyber situational awareness in cybersecurity systems. The ontology incorporates and integrates heterogeneous data and knowledge schemas from different cybersecurity systems and most commonly used cybersecurity standards for information sharing and exchange. The UCO ontology has also been mapped to a number of existing cybersecurity ontologies as well as concepts in the Linked Open Data cloud. Similar to DBpedia which serves as the core for general knowledge in Linked Open Data cloud, we envision UCO to serve as the core for cybersecurity domain, which would evolve and grow with the passage of time with additional cybersecurity data sets as they become available. We also present a prototype system and concrete use cases supported by the UCO ontology. To the best of our knowledge, this is the first cybersecurity ontology that has been mapped to general world ontologies to support broader and diverse security use cases. We compare the resulting ontology with previous efforts, discuss its strengths and limitations, and describe potential future work directions.
November 8th, 2015
In this report, we describe the Unified Cyber Security ontology (UCO) to support situational awareness in cyber security systems. The ontology is an effort to incorporate and integrate heterogeneous information available from different cyber security systems and most commonly used cyber security standards for information sharing and exchange. The ontology has also been mapped to a number of existing cyber security ontologies as well as concepts in the Linked Open Data cloud. Similar to DBpedia which serves as the core for Linked Open Data cloud, we envision UCO to serve as the core for the specialized cyber security Linked Open Data cloud which would evolve and grow with the passage of time with additional cybersecurity data sets as they become available. We also present a prototype system and concrete use-cases supported by the UCO ontology. To the best of our knowledge, this is the first cyber security ontology that has been mapped to general world ontologies to support broader and diverse security use-cases. We compare the resulting ontology with previous efforts, discuss its strengths and limitations, and describe potential future work directions.
November 5th, 2015
Extracting Structured Summaries
from Text Documents
Dr. Zareen Syed
Research Assistant Professor, UMBC
10:30am, Monday, 9 November 2015, ITE 346, UMBC
In this talk, Dr. Syed will present unsupervised approaches for automatically extracting structured summaries composed of slots and fillers (attributes and values) and important facts from articles, thus effectively reducing the amount of time and effort spent on gathering intelligence by humans using traditional keyword based search approaches. The approach first extracts important concepts from text documents and links them to unique concepts in Wikitology knowledge base. It then exploits the types associated with the linked concepts to discover candidate slots and fillers. Finally it applies specialized approaches for ranking and filtering slots to select the most relevant slots to include in the structured summary.
Compared with the state of the art, Dr. Syed’s approach is unrestricted, i.e., it does not require manually crafted catalogue of slots or relations of interest that may vary over different domains. Unlike Natural Language Processing (NLP) based approaches that require well-formed sentences, the approach can be applied on semi-structured text. Furthermore, NLP based approaches for fact extraction extract lexical facts and sentences that require further processing for disambiguating and linking to unique entities and concepts in a knowledge base, whereas, in Dr. Syed’s approach, concept linking is done as a first step in the discovery process. Linking concepts to a knowledge base provides the additional advantage that the terms can be explicitly linked or mapped to semantic concepts in other ontologies and are thus available for reasoning in more sophisticated language understanding systems.
September 29th, 2015
Clare Grasso, Anupam Joshi and ELior Siegel, Beyond NER: Towards Semantics in Clinical Text, Biomedical Data Mining, Modeling, and Semantic Integration (BDM2I); co-located with the 14th International Semantic Web Conference (ISWC 2015), Bethlehem, PA.
While clinical text NLP systems have become very effective in recognizing named entities in clinical text and mapping them to standardized terminologies in the normalization process, there remains a gap in the ability of extractors to combine entities together into a complete semantic representation of medical concepts that contain multiple attributes each of which has its own set of allowed named entities or values. Furthermore, additional domain knowledge may be required to determine the semantics of particular tokens in the text that take on special meanings in relation to this concept. This research proposes an approach that provides ontological mappings of the surface forms of medical concepts that are of the UMLS semantic class signs/symptoms. The mappings are used to extract and encode the constituent set of named entities into interoperable semantic structures that can be linked to other structured and unstructured data for reuse in research and analysis.
June 8th, 2015
Coldstart is a task in the NIST Text Analysis Conference’s Knowledge Base Population suite that combines entity linking and slot filling to populate an empty knowledge base using a predefined ontology for the facts and relations. This paper describes a system developed by the Human Language Technology Center of Excellence at Johns Hopkins University for the 2014 Coldstart task.
Tim Finin, Paul McNamee, Dawn Lawrie, James Mayfield and Craig Harman, Hot Stuff at Cold Start: HLTCOE participation at TAC 2014, 7th Text Analysis Conference, National Institute of Standards and Technology, Nov. 2014.
The JHU HLTCOE participated in the Cold Start task in this year’s Text Analysis Conference Knowledge Base Population evaluation. This is our third year of participation in the task, and we continued our research with the KELVIN system. We submitted experimental variants that explore use of forward-chaining inference, slightly more aggressive entity clustering, refined multiple within-document conference, and prioritization of relations extracted from news sources.
June 8th, 2015
The NSF-sponsored Platys project explored the idea that places are more than just GPS coordinates. They are concepts rich with semantic information, including people, activities, roles, functions, time and purpose. Our mobile phones can learn to recognize the places we are in and use information about them to provide better services.
Laura Zavala, Pradeep K. Murukannaiah, Nithyananthan Poosamani, Tim Finin, Anupam Joshi, Injong Rhee and Munindar P. Singh, Platys: From Position to Place-Oriented Mobile Computing, AI Magazine, v36, n2, 2015.
The Platys project focuses on developing a high-level, semantic notion of location called place. A place, unlike a geospatial position, derives its meaning from a user’s actions and interactions in addition to the physical location where it occurs. Our aim is to enable the construction of a large variety of applications that take advantage of place to render relevant content and functionality and, thus, improve user experience. We consider elements of context that are particularly related to mobile computing. The main problems we have addressed to realize our place-oriented mobile computing vision are representing places, recognizing places, and engineering place-aware applications. We describe the approaches we have developed for addressing these problems and related subproblems. A key element of our work is the use of collaborative information sharing where users’ devices share and integrate knowledge about places. Our place ontology facilitates such collaboration. Declarative privacy policies allow users to specify contextual features under which they prefer to share or not share their information.